agent_boot
Start or resume autonomous agent work in one token-budgeted call: retrieve session state, checkpoint summary, open tasks, handoff, lessons, facts, goals, skills, and repo map before proceeding.
Instructions
Boot an autonomous agent: ONE token-budgeted call returning everything needed to start or resume work. Call this FIRST in any agent run. Returns {agent, session:{...,role}, resume:{checkpoint_summary, open_tasks}, handoff:{tldr, source}, lessons:[], facts:[], brief, skills:[], skills_full, repo_map, siblings:[], budget:{limit, used, dropped}, client}. If a non-terminal session exists for this agent (or session_id is given), resume tells you exactly where you left off; handoff is the best-ranked latest handoff (a hand-written wrap SEED first). goal drives the facts, lessons AND skills retrieval. skills are parametrized procedures distilled from verified past runs matching the goal ({context_id, name, description, success_count, similarity}) -- check them BEFORE re-deriving a solution. On a session's later boots skills holds only new or changed entries and skills_full is false (empty then means nothing new, not no skills); pass full:true for the complete set. With project_id you also get a goal-graph brief {north_star, role, lane, next, blocked_on, blocking, done} and the session role is inferred from the matched goal node. With include_repo_map:true on a code-indexed workspace, repo_map carries top-ranked file signatures to answer "where is X handled" without grepping. siblings lists other active sessions in this workspace (last ~60 min, max 5) so you can coordinate via relay_* before touching shared resources. Slots fill resume > handoff > lessons > facts > brief; overflow is reported in budget.dropped. Trigger: resume or catch up on tracked work ("hôm trước tới đâu", "tiếp gì", "tóm lại đang làm gì", "what's next", "resume", "where did we leave off", "catch me up"). Skip for unrelated casual questions.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| full | No | T506: bypass the skills diff-since-last-boot behavior and always return the full current skills match set. Default false (repeat boots of the same session return only new/changed skills). | |
| goal | No | The objective for this run — drives relevant-facts + lessons retrieval AND goal-node role inference | |
| agent | Yes | Stable agent slug (handle the agent boots with every run, e.g. 'claude-code') | |
| workspace | No | Workspace slug to scope handoff + facts to | |
| agent_name | No | Human-readable name; used only when the agent is first created | |
| project_id | No | Project id to scope the goal-graph situation brief + role inference to (omit = no brief, classic pack) | |
| session_id | No | Resume a specific session by id (otherwise the latest active/paused session for this agent) | |
| token_budget | No | Max tokens for the assembled pack (default 4000) | |
| epistemic_min | No | Epistemic floor (T358) for the FACTS slot: only surface facts at or above this confidence tier (weakest->strongest: assumed < inferred < told < observed). Omit for no floor. | |
| include_repo_map | No | When true, include a token-budgeted repo map (entries with path+signatures) from code-indexed contexts. Only useful for workspaces indexed with contextq index. Default false. | |
| repo_map_token_budget | No | Token cap for the repo map slot (default ~2000, range 100-16000). Ignored when include_repo_map is false. |